In [4]:
plot_time_series('D',D_Feature_List)
######################### Plotting 13 columns with prefix D #########################
# LOAD LIBRARIES
import pandas as pd, numpy as np
import matplotlib.pyplot as plt
from matplotlib import gridspec
# LOAD TRAIN DATA AND MERGE TARGETS ONTO FEATURES
#df = pd.read_csv('./amex-default-prediction/train_data.csv', nrows=100_0000)
#df.S_2 = pd.to_datetime(df.S_2)
#df2 = pd.read_csv('./amex-default-prediction/train_labels.csv')
df = pd.read_parquet('./amex-parquet/train.parquet')
df.S_2 = pd.to_datetime(df.S_2)
df2 = pd.read_csv('./amex-default-prediction/train_labels.csv')
df = df.merge(df2,on='customer_ID',how='left')
def plot_time_series(prefix='D', cols=None, display_ct=32):
# DETERMINE WHICH COLUMNS TO PLOT
if cols is not None and len(cols)==0: cols = None
if cols is None:
COLS = df.columns[2:-1]
COLS = np.sort( [int(x[2:]) for x in COLS if x[0]==prefix] )
COLS = [f'{prefix}_{x}' for x in COLS]
print('#'*25)
print(f'Plotting all {len(COLS)} columns with prefix {prefix}')
print('#'*25)
else:
COLS = [f'{prefix}_{x}' for x in cols]
print('#'*25)
print(f'Plotting {len(COLS)} columns with prefix {prefix}')
print('#'*25)
# ITERATE COLUMNS
for c in COLS:
# CONVERT DATAFRAME INTO SERIES WITH COLUMN
tmp = df[['customer_ID','S_2',c,'target']].copy()
tmp2 = tmp.groupby(['customer_ID','target'])[['S_2',c]].agg(list).reset_index()
tmp3 = tmp2.loc[tmp2.target==1]
tmp4 = tmp2.loc[tmp2.target==0]
# FORMAT PLOT
spec = gridspec.GridSpec(ncols=2, nrows=1,
width_ratios=[3, 1], wspace=0.1,
hspace=0.5, height_ratios=[1])
fig = plt.figure(figsize=(20,10))
ax0 = fig.add_subplot(spec[0])
# PLOT 32 DEFAULT CUSTOMERS AND 32 NON-DEFAULT CUSTOMERS
t0 = []; t1 = []
for k in range(display_ct):
try:
# PLOT DEFAULTING CUSTOMERS
row = tmp3.iloc[k]
ax0.plot(row.S_2,row[c],'-o',color='blue')
t1 += row[c]
# PLOT NON-DEFAULT CUSTOMERS
row = tmp4.iloc[k]
ax0.plot(row.S_2,row[c],'-o',color='orange')
t0 += row[c]
except:
pass
plt.title(f'Feature {c} (Key: BLUE=DEFAULT, orange=no default)',size=18)
# PLOT HISTOGRAMS
ax1 = fig.add_subplot(spec[1])
try:
# COMPUTE BINS
t = t0+t1; mn = np.nanmin(t); mx = np.nanmax(t)
if mx==mn:
mx += 0.01; mn -= 0.01
bins = np.arange(mn,mx+(mx-mn)/20,(mx-mn)/20 )
# PLOT HISTOGRAMS
if np.sum(np.isnan(t1))!=len(t1):
ax1.hist(t1,bins=bins,orientation="horizontal",alpha = 0.8,color='blue')
if np.sum(np.isnan(t0))!=len(t0):
ax1.hist(t0,bins=bins,orientation="horizontal",alpha = 0.8,color='orange')
except:
pass
plt.show()
D_Feature_List = [48,54,55,58,61,62,74,75,77,80,115,118,119]
# S_Feature_List = All
# P_Feature_List = All
B_Feature_List = [1,3,4,7,9,19,20,23,28,33,37,40]
R_Feature_List = [9,10,26,27]
plot_time_series('D',D_Feature_List)
######################### Plotting 13 columns with prefix D #########################
plot_time_series('S')
######################### Plotting all 21 columns with prefix S #########################
--------------------------------------------------------------------------- KeyboardInterrupt Traceback (most recent call last) c:\Users\minda\Documents\AI_project\amex-project(EDA)_Plot_Picked.ipynb 셀 8 in <cell line: 1>() ----> <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=0'>1</a> plot_time_series('S') c:\Users\minda\Documents\AI_project\amex-project(EDA)_Plot_Picked.ipynb 셀 8 in plot_time_series(prefix, cols, display_ct) <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=18'>19</a> for c in COLS: <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=19'>20</a> <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=20'>21</a> # CONVERT DATAFRAME INTO SERIES WITH COLUMN <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=21'>22</a> tmp = df[['customer_ID','S_2',c,'target']].copy() ---> <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=22'>23</a> tmp2 = tmp.groupby(['customer_ID','target'])[['S_2',c]].agg(list).reset_index() <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=23'>24</a> tmp3 = tmp2.loc[tmp2.target==1] <a href='vscode-notebook-cell:/c%3A/Users/minda/Documents/AI_project/amex-project%28EDA%29_Plot_Picked.ipynb#X10sZmlsZQ%3D%3D?line=24'>25</a> tmp4 = tmp2.loc[tmp2.target==0] File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\groupby\generic.py:883, in DataFrameGroupBy.aggregate(self, func, engine, engine_kwargs, *args, **kwargs) 878 if result is None: 879 880 # grouper specific aggregations 881 if self.grouper.nkeys > 1: 882 # test_groupby_as_index_series_scalar gets here with 'not self.as_index' --> 883 return self._python_agg_general(func, *args, **kwargs) 884 elif args or kwargs: 885 # test_pass_args_kwargs gets here (with and without as_index) 886 # can't return early 887 result = self._aggregate_frame(func, *args, **kwargs) File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\groupby\groupby.py:1490, in GroupBy._python_agg_general(self, func, *args, **kwargs) 1486 name = obj.name 1488 try: 1489 # if this function is invalid for this dtype, we will ignore it. -> 1490 result = self.grouper.agg_series(obj, f) 1491 except TypeError: 1492 warn_dropping_nuisance_columns_deprecated(type(self), "agg") File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\groupby\ops.py:972, in BaseGrouper.agg_series(self, obj, func, preserve_dtype) 969 result = self._aggregate_series_pure_python(obj, func) 971 elif not isinstance(obj._values, np.ndarray): --> 972 result = self._aggregate_series_pure_python(obj, func) 974 # we can preserve a little bit more aggressively with EA dtype 975 # because maybe_cast_pointwise_result will do a try/except 976 # with _from_sequence. NB we are assuming here that _from_sequence 977 # is sufficiently strict that it casts appropriately. 978 preserve_dtype = True File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\groupby\ops.py:1003, in BaseGrouper._aggregate_series_pure_python(self, obj, func) 1000 # equiv: splitter = self._get_splitter(obj, axis=0) 1001 splitter = get_splitter(obj, ids, ngroups, axis=0) -> 1003 for i, group in enumerate(splitter): 1004 group = group.__finalize__(obj, method="groupby") 1005 res = func(group) File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\groupby\ops.py:1233, in DataSplitter.__iter__(self) 1230 starts, ends = lib.generate_slices(self.slabels, self.ngroups) 1232 for start, end in zip(starts, ends): -> 1233 yield self._chop(sdata, slice(start, end)) File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\groupby\ops.py:1246, in SeriesSplitter._chop(self, sdata, slice_obj) 1244 def _chop(self, sdata: Series, slice_obj: slice) -> Series: 1245 # fastpath equivalent to `sdata.iloc[slice_obj]` -> 1246 mgr = sdata._mgr.get_slice(slice_obj) 1247 # __finalize__ not called here, must be applied by caller if applicable 1248 return sdata._constructor(mgr, name=sdata.name, fastpath=True) File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\internals\managers.py:1827, in SingleBlockManager.get_slice(self, slobj, axis) 1824 raise IndexError("Requested axis not found in manager") 1826 blk = self._block -> 1827 array = blk._slice(slobj) 1828 bp = BlockPlacement(slice(0, len(array))) 1829 block = type(blk)(array, placement=bp, ndim=1) File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\internals\blocks.py:313, in Block._slice(self, slicer) 310 def _slice(self, slicer) -> ArrayLike: 311 """return a slice of my values""" --> 313 return self.values[slicer] File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\arrays\datetimelike.py:341, in DatetimeLikeArrayMixin.__getitem__(self, key) 333 """ 334 This getitem defers to the underlying array, which by-definition can 335 only handle list-likes, slices, and integer scalars 336 """ 337 # Use cast as we know we will get back a DatetimeLikeArray or DTScalar, 338 # but skip evaluating the Union at runtime for performance 339 # (see https://github.com/pandas-dev/pandas/pull/44624) 340 result = cast( --> 341 "Union[DatetimeLikeArrayT, DTScalarOrNaT]", super().__getitem__(key) 342 ) 343 if lib.is_scalar(result): 344 return result File c:\Users\minda\.conda\envs\tf20\lib\site-packages\pandas\core\arrays\_mixins.py:280, in NDArrayBackedExtensionArray.__getitem__(self, key) 277 # error: Incompatible types in assignment (expression has type "ExtensionArray", 278 # variable has type "Union[int, slice, ndarray]") 279 key = extract_array(key, extract_numpy=True) # type: ignore[assignment] --> 280 key = check_array_indexer(self, key) 281 result = self._ndarray[key] 282 if lib.is_scalar(result): KeyboardInterrupt:
plot_time_series('P')
######################### Plotting all 3 columns with prefix P #########################
plot_time_series('B',B_Feature_List)
######################### Plotting 11 columns with prefix B #########################
plot_time_series('R',R_Feature_List)
######################### Plotting 3 columns with prefix R #########################
